This is f*cking insane. Andrej Karpathy:
"Prompting is going away. Delete everything, keep Graph."
In just 69 minutes, he shows how to build graphs and why they're the only layer left standing in the end
Prompts → Agents → Loops → Graphs
a loop keeps one agent working until the job is done
a graph decides which agents exist and what each one hands to the next
anyone can build an agent, almost nobody builds the graph that runs them
watch it today, then save the full guide on graphs below before everyone else catches up ↓
👇 BEST EXPLANATION EVER ON HOW LLMS ARE BUILT
it's surprisingly simple when you break it down!
1️⃣ Gather and clean enormous amounts of data.
2️⃣ Convert text into tokens and vectors.
3️⃣ Train transformers to recognize patterns.
4️⃣ Predict the next token billions of times, improving each time.
5️⃣ Refine with feedback and reward signals.
6️⃣ Compress and optimize for real-world use.
but here's the fascinating thing:
nobody hardcoded the ability to write software, solve problems or explain science.
much of it emerged from one simple task: predicting what comes next.
and we're still discovering what else they can do.
🚨 ESTO ES UNA LOCURA
Un desarrollador chino ha liberado un modelo OCR capaz de procesar documentos completos sin perder el contexto entre páginas.
Se llama Unlimited-OCR y puede hacer cosas como 👇
→ Extraer texto, tablas y fórmulas
→ Mantener el orden correcto de lectura
→ Procesar PDFs multipágina de una sola pasada
→ Trabajar con varios idiomas
→ Ejecutarse en local con vLLM, SGLang, Ollama o LM Studio
Lo interesante está en cómo maneja documentos largos.
Está diseñado para procesar página tras página manteniendo el contexto, lo que llaman long-horizon parsing.
Tiene solo 3.000 millones de parámetros, licencia MIT y ya supera 1,2 millones de descargas en un mes.
Y sí, los pesos son abiertos.
Repo en comentarios 👇
ACABAN DE FILTRAR EL EDITOR DE PDF QUE DEJA A ADOBE SIN CLIENTES
Se llama RevPDF, hace lo mismo que Adobe, es gratis y pesa solo 20 MB.
Es un editor de PDF open source que funciona directamente en tu equipo, sin cuentas, sin suscripciones y sin subir tus archivos a ningún servidor.
Con él puedes:
→ Editar texto e imágenes directamente sobre el documento
→ Firmar contratos y formularios
→ Censurar datos sensibles antes de compartir
→ Comprimir el archivo para enviarlo más rápido
→ Pasar el PDF a Word
Funciona sin conexión, así que tus documentos privados no salen de tu ordenador.
Si trabajas con contratos, facturas o documentos a diario, esta herramienta te ahorra una suscripción entera.
Guárdalo para cuando lo necesites.
Link aquí ↓
Google isn’t trying to win the AI race.
They’re trying to own the entire AI Agent ecosystem.
While everyone argues ChatGPT vs Claude, Google quietly built:
Models → Gemini Pro, Flash, Deep Think, Gemma
Design → Stitch, Whisk, Imagen
Research → NotebookLM, AI Mode
Video → Veo, Flow, Google Vids
Coding → Antigravity IDE, Gemini CLI, Jules
Agents → A2A, ADK, FileSearch API
The scary part?
All of these tools talk to each other.
That means:
10x faster prototypes
End-to-end AI workflows
Production-ready agents on GCP
The next AI war won’t be model vs model.
It’ll be ecosystem vs ecosystem.
Save. Share. Build.
🚨ESTO ACABA DE MATAR A ELEVENLABS
74.000 personas ya lo han guardado en GitHub y casi nadie habla de ello.
Se llama VoiceStudio y es un reemplazo 100% gratis que corre en tu propio ordenador.
Te permite:
→ Clonar tu propia voz
→ Doblar vídeos a 646 idiomas
→ Crear audiolibros y dictar
→ Elegir entre 17 motores
Sin pago por carácter.
Sin límites de uso.
Todo en tu máquina.
🔖 Guárdalo.
This is Pele, my new rendering library for diagrams and charts, compatible with the latest Mermaid syntax.
- 100-500× faster than mermaid.js
- 6× smaller bundle
- No dependencies
- Easy to theme
- Responsive to device width
In pursuit of making Obsidian insanely fast and cohesively designed, I always found the Mermaid library to be too big, too slow, and too hard to theme. Pele will be the new renderer in the next version of Obsidian, but you can start using it now.
Pele [ˈpɛlɛ] is named after the goddess of volcanoes and fire. It's open source under the MIT license. Try the playground!
Today is my birthday. Here's my gift to you all.
Introducing: Muxin - one app for all my computers.
Macs, Linux servers, Windows PCs, cloud machines. I run AI coding agents on all of them from one window, and my agents can use it too.
Free and open source. 🧵
this one page turns Obsidian + Opus 5.5 + Jev into a second brain that thinks with you around the clock
built on Karpathy's ideas
Jev reads every note before Opus does
Opus writes only what matters
your vault keeps working while you don't
cuts 80% off your weekly chat time
frees you up for the work your manager actually pays for
the people who set this up early
are the ones the next raise finds first
UN CHINO HA REVENTADO EL OCR:
1,2 MILLONES DE DESCARGAS EN UN MES
Baidu acaba de liberar Unlimited-OCR.
Gratis, pesos abiertos, licencia MIT.
¿Qué hace?
Le metes un documento, una foto, un escaneo, un PDF entero y te lo devuelve como texto limpio y estructurado.
Tablas, fórmulas, el orden de lectura, todo.
Lo diferente está en el nombre: Unlimited.
Los modelos de OCR se ahogan con documentos largos.
Este está hecho para tragarse un PDF entero de una sola pasada, página tras página, sin perder el hilo.
Ellos lo llaman “parsing de horizonte largo”.
→ Documentos con texto, tablas y fórmulas, en estructura
→ Multipágina y PDF de corrido
→ Multilingüe
→ Solo 3.000 millones de parámetros: ligero, corre en una GPU normal
→ Y lo puedes levantar en local con vLLM, SGLang, Ollama o LM Studio
Es la respuesta de Baidu a DeepSeek-OCR, y lo dicen abiertamente: querían llevarlo un paso más allá.
4.400 likes en Hugging Face. 1,2 millones de descargas el mes pasado. MIT.
Link en los comentarios 👇🏻
Sam Altman (CEO of Open AI):
"You no longer need to write prompts."
In just 38 minutes, he explains how to use ChatGpt at a level that most people can't even imagine.
It's talk he gave to stanford students. A friend sent me the recording last night.
After watching it, I realized I was only taking advantage of about 15% of what this tool can really do.
Watch it in full and then read the guide l leave below on how to create a system that prompts itself.
Andrej Karpathy spent 8 years at OpenAI and Tesla
last week, he packed everything he knows into one free 2-hour lecture
Agents → Loops → Harness → Self-Improving Systems
people spend $25K on bootcamps that teach less than this
this lecture is worth more than most paid AI engineering courses
you probably don't have two hours for it right now
don't let it get buried in your feed
bookmark it and watch later
then read the full article below
If you're struggling with `useEffect`, don't worry.
Even senior React devs struggle with it.
Yes, that large dependency array and complicated if-statement you have in there is... typical.
It's just an awkward hook, okay?